Deep Learning XAI for Bus Passenger Forecasting: A Use Case in Spain
Time series forecasting of passenger demand is crucial for optimal planning of limited resources. For smart cities, passenger transport in urban areas is an increasingly important problem, because the construction of infrastructure is not the solution and the use of public transport should be encour...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2022 |
| País: | España |
| Institución: | Universidad Complutense de Madrid (UCM) |
| Repositorio: | Docta Complutense |
| Idioma: | inglés |
| OAI Identifier: | oai:docta.ucm.es:20.500.14352/114680 |
| Acceso en línea: | https://hdl.handle.net/20.500.14352/114680 |
| Access Level: | acceso abierto |
| Palabra clave: | 656.025.2 004.8 519.216.3 Deep learning LSTM XAI Time series Passenger forecasting Smart city Surrogate model 2-tuple fuzzy model Inteligencia artificial (Informática) Estadísticas e indicadores sociales 1203.04 Inteligencia Artificial 1209.14 Técnicas de Predicción Estadística 3329.07 Transporte |
| Sumario: | Time series forecasting of passenger demand is crucial for optimal planning of limited resources. For smart cities, passenger transport in urban areas is an increasingly important problem, because the construction of infrastructure is not the solution and the use of public transport should be encouraged. One of the most sophisticated techniques for time series forecasting is Long Short Term Memory (LSTM) neural networks. These deep learning models are very powerful for time series forecasting but are not interpretable by humans (black-box models). Our goal was to develop a predictive and linguistically interpretable model, useful for decision making using large volumes of data from different sources. Our case study was one of the most demanded bus lines of Madrid. We obtained an interpretable model from the LSTM neural network using a surrogate model and the 2-tuple fuzzy linguistic model, which improves the linguistic nterpretability of the generated Explainable Artificial Intelligent (XAI) model without losing precision |
|---|